CVE-2026-26220
Published: 17 February 2026
Summary
CVE-2026-26220 is a critical-severity Deserialization of Untrusted Data (CWE-502) vulnerability. Its CVSS base score is 9.3 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 46.9th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
Deeper analysis
LightLLM versions 1.1.0 and prior contain an unauthenticated remote code execution vulnerability in PD disaggregation mode. The PD master node exposes WebSocket endpoints that receive binary frames and pass the data directly to pickle.loads without authentication or validation, a flaw tracked as CWE-502.
A remote attacker who can reach the PD master node can send a crafted binary payload over the exposed WebSocket endpoints to trigger arbitrary code execution on the server, achieving full control over the affected component.
The provided references point to a technical analysis and the upstream GitHub issue but contain no details on official patches or mitigation steps. The associated EPSS scores remain low, with a current value of 0.0115 and a recorded peak of 0.0150.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-7823
Vulnerability details
LightLLM version 1.1.0 and prior contain an unauthenticated remote code execution vulnerability in PD (prefill-decode) disaggregation mode. The PD master node exposes WebSocket endpoints that receive binary frames and pass the data directly to pickle.loads() without authentication or validation. A…
more
remote attacker who can reach the PD master can send a crafted payload to achieve arbitrary code execution.
- CWE(s)
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Unauthenticated RCE via unsafe pickle deserialization on exposed WebSocket service directly enables exploitation of public-facing app (T1190) and Python interpreter abuse (T1059.006).
CVEs Like This One
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Penetration testing supplies malicious serialized objects, detecting unsafe deserialization and supporting corrective actions.
Evaluation of untrusted data handling (deserialization testing) reveals unsafe processing, which the required remediation process addresses.
Untrusted serialized data can be deserialized and observed inside the chamber, blocking gadget-chain exploitation outside the sandbox.
Validates or rejects untrusted serialized data before deserialization occurs.
Identifies and blocks malicious code introduced through deserialization of untrusted data at system boundaries.
Integrity verification of serialized information can detect tampering before deserialization occurs.
Provenance of associated data allows detection of untrusted sources before deserialization or processing occurs.